TJian

Awesome Large Action Model (LAM): Models that could help gets things done.

No description.

No description.

No description.

A framework for efficient model inference with omni-modality models

A high-throughput and memory-efficient inference and serving engine for LLMs

FlyDSL is the Python front‑end of the project: Flexible LaYout DSL.

Modern RL Post-training Infrastructure: Optimized for NVIDIA/AMD GPUs with a focus on vLLM and DeepSpeed integration, CUDA/ROCm/Triton kernels, and transparent hardware-aware scaling.

Fun Learning

All parts of Claude Code's system prompt, 24 builtin tool descriptions, sub agent prompts (Plan/Explore/Task), utility prompts (CLAUDE.md, compact, statusline, magic docs, WebFetch, Bash cmd, security review, agent creation). Updated for each Claude Code version.

Stateful API logic for agentic applications using vLLM

No description.

No description.

No description.

No description.

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

Ring attention implementation with flash attention

The code used to train and run inference with the ColPali architecture.

No description.

Course Material for the UG Course COMP4901Y

The Supabase for RAG - R2R lets you build, scale, and manage user-facing Retrieval-Augmented Generation applications

Windows system utilities to maximize productivity

No description.

Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.

No description.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

No description.

No description.

MediaPipe is a cross-platform framework for building multimodal applied machine learning pipelines

The official Node.js / Typescript library for the OpenAI API

No description.

Interact privately with your documents using the power of GPT, 100% privately, no data leaks

Inference code for LLaMA models

No description.

VSCode extension that allows you to use ChatGPT or GPT4 inside the IDE

EAGLE: Lossless Acceleration of LLM Decoding by Feature Extrapolation

Gorilla: An API store for LLMs

[NeurIPS 2023 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

No description.

No description.

A small extention pypi library to serve fastchat through different apis. Currently supports openai api.

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

vscode-extension to connect to gpt

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

NewHope: Harnessing 99% of GPT-4's Programming Capabilities

Pyminio is a python client wrapped like the os module to control minio server

The official repository of "Video assistant towards large language model makes everything easy"

Run hugging face spaces locally with one command!

No description.

PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images

A portable x64 and x86 OpenGL CMake workspace template for Windows, Linux and WSL

Traffic Sign Detection. Code for the paper entitled "Evaluation of deep neural networks for traffic sign detection systems".

OpenMMLab Text Detection, Recognition and Understanding Toolbox

Paper reading notes on Deep Learning and Machine Learning

Official PyQt implementation of 3D bbox annotation tool for CenterLoc3D

Point-NeRF: Point-based Neural Radiance Fields

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

LiDAR point cloud ground filtering / segmentation (bare earth extraction) method based on cloth simulation

Google Colab Notebooks for Udacity CS344 - Intro to Parallel Programming

Official Python Implementation for "3D Multi-Object Tracking: A Baseline and New Evaluation Metrics", IROS 2020, ECCVW 2020

My solutions to Udacity's Parallel Programming course (CS 344)

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

No description.

The English version of 14 lectures on visual SLAM.

The G3D Innovation Engine by Morgan McGuire

Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.

No description.

Opengl c++ template for vscode ide

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.

No description.

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

No description.

No description.

No description.

A lightweight tool for labeling 3D bounding boxes in point clouds.

PU-Net: Point Cloud Upsampling Network, CVPR, 2018 (https://arxiv.org/abs/1801.06761)

waymo open data utils

OpenMMLab Detection Toolbox and Benchmark

OpenMMLab Computer Vision Foundation

OpenMMLab's next-generation platform for general 3D object detection.

A custom GPU & CPU op for tensorflow to calculate the rotated/skew IOU of two lists of boxes.

Potree/Entwine interactivity demo

Entwine - point cloud organization for massive datasets

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

No description.

Indoor Location Competition 2.0

No description.

No description.

No description.

prnet

ICP implementation for PyTorch CUDA extension

A high performance CUDA implementation of Scan Matching via the Iterative Closest Point Algorithm

CUDA based Iterative Closest Point Algorithm Implementation

3d lidar point cloud 2d image projection in python.

Differentiable Point Cloud Sampling (CVPR 2020 Oral)

Open3D: A Modern Library for 3D Data Processing

TensorFlow documentation

🔥RandLA-Net in Tensorflow (CVPR 2020, Oral) https://stackoverflow.com/questions/4470523/create-a-branch-in-git-from-another-branch

PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud, CVPR 2019.

an experiment for yolo-v1, including training and testing.

Implementation of Convolutional LSTM in PyTorch.

TensorFlow implementation of PointRNN, PointGRU and PointLSTM.

Open MMLab Image and Video Super-Resolution Toolbox, , including SRResNet, SRGAN, ESRGAN, EDVR, etc.

The py version of toflow → https://github.com/anchen1011/toflow

Ouster sample code

A python parser for DBLP dataset

Multi-level Wavelet Convolutional Neural Networks

Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet

TOFlow: Video Enhancement with Task-Oriented Flow

pytorch structural similarity (SSIM) loss

This is a small Python library for sending data over sockets.

Image processing course

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks

Reduction of Video Compression Artifacts Based on Deep Temporal Networks (IEEE Access, 2018)

This repo will contain source code and materials for the TecoGAN project, i.e. code for a TEmporally COherent GAN

No description.

Mind-aware Multi-agent Management Reinforcement Learning

Deep reinforcement learning in Minecraft using gym-minecraft and keras-rl.

Multi Agent Reinforcement Learning using MalmÖ

Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

Code for "Fast Context Adaptation via Meta-Learning"

Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

No description.

The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.

Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

Use the Mask RCNN for the human pose estimation

Models and examples built with TensorFlow

No description.

A faster pytorch implementation of faster r-cnn

Deep Learning for humans

Microsoft x DJI Drones Competition

Python code, PDFs and resources for the series of posts on Reinforcement Learning which I published on my personal blog

A robot powered training repository :robot:

In this project, we constructed a relational database using python 3.5, qt designer and mysql. The mysql servers is a remote server setup by the Georgia Institute of Technology. Thus, after this Fall 2018 semester the database might not be able to be accessed anymore.

This is a Data Mining course offered by The Hong Kong University of Science and Technology

Data Visualisation. Project Title: Formula 1

A set of C++ classes that provide a common API for realtime audio input/output across Linux (native ALSA, JACK, PulseAudio and OSS), Macintosh OS X (CoreAudio and JACK), and Windows (DirectSound, ASIO, and WASAPI) operating systems.

RM devboard embedded developement with ChibiOS

Integration project for RM infantry embedded program

No description.

RoboRTS infantry control firmware

Serial Tuner GUI written in Python